From mboxrd@z Thu Jan 1 00:00:00 1970 From: Wei Wang2 Subject: Re: [PATCH] AMD IOMMU: Use global interrupt remapping table by default Date: Thu, 21 Jul 2011 12:38:15 +0200 Message-ID: <201107211238.15699.wei.wang2@amd.com> References: <200910281732.07420.wei.wang2@amd.com> <201107201756.45241.wei.wang2@amd.com> Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Return-path: In-Reply-To: Content-Disposition: inline List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xensource.com Errors-To: xen-devel-bounces@lists.xensource.com To: George Dunlap Cc: Ian Campbell , "xen-devel@lists.xensource.com" List-Id: xen-devel@lists.xenproject.org On Thursday 21 July 2011 11:07:40 George Dunlap wrote: > On Wed, Jul 20, 2011 at 4:56 PM, Wei Wang2 wrote: > > George & Ian, > > Patch attached. This patch removes global interrupt remapping table and > > uses per-device table instead. This should work with per-cpu IDTs. =A0We > > are safe to remove global table since SATA device id issue dose not > > appear in recent production BIOS. > > Exactly how "recent" are these BIOSes? Or I guess alternately, how > old are the BIOSes that broke? George, Actually, we encountered this issue about 2 years ago and fixed this in BIO= S.=20 There should be very less productions shipped the mark at that time (probab= ly=20 none) and all newer products after that should absorb this fix. Even withou= t=20 BIOS fix, user can always disable IDE mode from BIOS menu manually if they= =20 were hit by this issue. So basically, I think removing global table is also= =20 reasonable. =20 Thanks Wei > We still have customers who seem to have hardware that's several years > old; if the answer isn't something like "8 years", it may be better to > just change the default setting. > > -George